Voice Inquiry Response via Relation Graph Across Databases

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing electronic devices face challenges in providing precise responses to user inquiries across multiple databases, requiring separate integration processes and struggling with systematic interlocking of different data types and manufacturer-specific devices.

Innovation Solution

An electronic device utilizing a relation graph to generate inquiries and manage responses from multiple databases, performing voice recognition, and generating responses based on acquired data, thereby eliminating the need for separate database integration and enabling systematic connection across various database types.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If a separate database integrating multiple databases is generated, then response data can be acquired from multiple databases, but device complexity and integration difficulty increase

Engineering Contradiction:

Improveability to acquire response data from multiple databasesVSAvoidcomplexity of database integration

Core Design Contradiction:

Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent introduces a relation graph as an intermediary data structure that models relationships between entities across multiple databases. Instead of physically integrating databases, the relation graph serves as a mediator that connects different data sources through entity relationships, enabling unified querying without direct database integration

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The patent creates a virtual copy of the database structure in the form of a relation graph. This graph copies the essential entity relationships from multiple databases without duplicating the actual data, allowing the system to query across databases through the graph model rather than through complex integration

Inventive Principle:

Principle #26Copying

2Ease of operation

If preliminary definition of intent and parameters is required for voice commands, then voice processing can be performed, but adaptability to new data types and systematic interlocking becomes difficult

Engineering Contradiction:

Improvevoice command processing capabilityVSAvoidability to interlock with new data types

Core Design Contradiction:

Ease of operationVSAdaptability or versatility

Solution Approach 1:

The patent implements a dynamic intent recognition system that learns from the relation graph structure. Instead of requiring fixed preliminary definitions, the system dynamically adapts to new data types by leveraging the entity relationships already modeled in the graph, allowing flexible interpretation of voice commands across diverse data domains

Inventive Principle:

Principle #15Dynamics

Solution Approach 2:

The relation graph serves as a universal framework that can represent multiple data types and domains through a common entity relationship model. This universal structure enables the voice processing system to handle various data types without requiring separate definition schemes for each type

Inventive Principle:

Principle #6Universality (Multi-functionality)

3Ease of manufacture

If conventional rule-based smart systems are used, then initial implementation is straightforward, but recognition rate and understanding of user preference deteriorate over time

Engineering Contradiction:

Improveease of initial implementationVSAvoidrecognition rate and user preference understanding

Core Design Contradiction:

Ease of manufactureVSMeasurement precision

Solution Approach 1:

The patent performs preliminary structuring of data into a relation graph that captures entity relationships before voice processing occurs. This pre-organized structure enables more accurate recognition and understanding by providing a structured framework that guides the interpretation of user inquiries, improving precision while maintaining implementation feasibility

Inventive Principle:

Principle #10Preliminary action

Data Source

PatentUS11328719B2Electronic device and method for controlling the electronic device

Publication Date: 2022.05.10 SAMSUNG ELECTRONICS CO LTD

AI summary

An electronic device and a method for controlling the electronic device is provided. The electronic device includes a microphone, a memory configured to include at least one instruction, and a processor configured to execute the at least one instruction. The processor is configured to control the electronic device to perform voice recognition for an inquiry based on receiving input of a user inquiry through the microphone, and acquire a text for the inquiry, generate a plurality of inquiries for acquiring response data for the inquiry from a plurality of databases using a relation graph indicating a relation between the acquired text and data stored in the plurality of databases, acquire response data corresponding to each of the plurality of inquiries from each of the plurality of databases, and generate a response for the inquiry based on the response data acquired from each of the plurality of databases and output the response.